© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125361
    Prev
    Next
    INDEX
    Explanations

    references to Cuba and its related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abel
    -0.07
    ive
    -0.06
    oud
    -0.06
    oret
    -0.06
     Pike
    -0.06
    lich
    -0.05
    ship
    -0.05
    bred
    -0.05
    erer
    -0.05
    ables
    -0.05
    POSITIVE LOGITS
    anness
    0.09
    0.07
     Missile
    0.07
    icrous
    0.07
     Cub
    0.07
     island
    0.07
    atem
    0.07
    è¡Ĺéģĵ
    0.07
    erculosis
    0.07
    ernal
    0.07
    Activations Density 0.014%

    No Known Activations